{"id":"https://openalex.org/W3138614542","doi":"https://doi.org/10.1109/bigdata50022.2020.9377866","title":"ReSpark: Automatic Caching for Iterative Applications in Apache Spark","display_name":"ReSpark: Automatic Caching for Iterative Applications in Apache Spark","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3138614542","doi":"https://doi.org/10.1109/bigdata50022.2020.9377866","mag":"3138614542"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031688318","display_name":"Michael J. Mior","orcid":"https://orcid.org/0000-0002-4057-8726"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Mior","raw_affiliation_strings":["Department of Computer Science, Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035977189","display_name":"Kenneth Salem","orcid":"https://orcid.org/0000-0003-0409-9725"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kenneth Salem","raw_affiliation_strings":["Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2342,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.4673189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7976944446563721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7585943937301636},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.451631635427475},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2224428951740265}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7976944446563721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585943937301636},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.451631635427475},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2224428951740265}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1854214752","https://openalex.org/W1974647172","https://openalex.org/W1981493461","https://openalex.org/W2013344760","https://openalex.org/W2096125134","https://openalex.org/W2108399535","https://openalex.org/W2120458882","https://openalex.org/W2124509324","https://openalex.org/W2133995768","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2381524109","https://openalex.org/W2413953908","https://openalex.org/W2547358264","https://openalex.org/W2566979091","https://openalex.org/W2584551900","https://openalex.org/W2592324943","https://openalex.org/W2963670827","https://openalex.org/W3118608800","https://openalex.org/W6639055396","https://openalex.org/W6687322159","https://openalex.org/W6710076213","https://openalex.org/W6715689577","https://openalex.org/W6729069003","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3015859229","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W1975949872","https://openalex.org/W2905242764","https://openalex.org/W3109411864","https://openalex.org/W3017846737","https://openalex.org/W3003280185","https://openalex.org/W2390279801"],"abstract_inverted_index":{"Apache":[0],"Spark":[1,17,52,86,107,114,121],"is":[2,19,76],"a":[3,23,99],"distributed":[4],"computing":[5],"framework":[6],"used":[7,69],"for":[8,41,101,112,130],"big":[9],"data":[10],"processing.":[11],"A":[12],"common":[13],"pattern":[14],"in":[15],"many":[16,113],"applications":[18,87,122],"to":[20,53,78,108,123],"iteratively":[21,61],"evolve":[22],"dataset":[24],"until":[25],"reaching":[26],"some":[27,32],"user-specified":[28],"convergence":[29],"condition.":[30],"Unfortunately,":[31],"aspects":[33],"of":[34,51,74,85],"Spark's":[35],"execution":[36],"model":[37],"make":[38],"it":[39],"difficult":[40],"developers":[42,84],"who":[43],"are":[44,59],"not":[45],"familiar":[46],"with":[47],"the":[48,128],"implementation-level":[49],"details":[50],"write":[54],"efficient":[55],"iterative":[56],"programs.Since":[57],"results":[58,63,93],"constructed":[60],"and":[62],"from":[64,125],"previous":[65],"iterations":[66],"may":[67],"be":[68,95],"multiple":[70],"times,":[71],"effective":[72],"use":[73],"caching":[75,110,126,132],"necessary":[77],"avoid":[79],"recomputing":[80],"intermediate":[81,92],"results.":[82],"Currently,":[83],"must":[88],"manually":[89],"indicate":[90],"which":[91],"should":[94],"cached.":[96],"We":[97,116],"present":[98],"method":[100],"using":[102],"metadata":[103],"already":[104],"captured":[105],"by":[106],"automate":[109],"decisions":[111],"programs.":[115],"show":[117],"how":[118],"this":[119],"allows":[120],"benefit":[124],"without":[127],"need":[129],"manual":[131],"annotations.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}